LitReviewBench - Literature Coverage: leaderboard

Metric: Expert-preference rating (Elo scale, Bradley-Terry aggregation of about 3,000 anonymized pairwise battles judged by matched domain experts on D1 literature coverage; literature review drafts on AI topics; the human-draft baseline is in the rating pool). Source: arxiv.org. Saturation forecast: Around March 2027. 9 models tracked.

Top models

#ModelScore
1Sonar Deep Research1175.9
2Claude Opus 4.51129
3Grok 4886.8
4Qwen 3 235B A22B759.3
5Gemini 2.5 Pro446.1
6GLM-4.6436.7

Interactive version: theaggregate.ai/benchmark?slug=litreviewbench-literature-coverage · How It Works · Data refreshed daily, snapshot 2026-09-26.